whwu95 / Text4Vis

【AAAI'2023 & IJCV】Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective

https://arxiv.org/abs/2207.01297

whwu95/Text4Vis Issues

model without text
Updated 5 months ago
数据并行or模型并行
Updated 5 months ago
回归任务
Updated 5 months ago
Could you provide the code/setting/threshold for producing Figure 1?
Closed 6 months ago1
lda_0.1.pt等文件
Updated 7 months ago6
CoOP
Updated 7 months ago1
关于多模态融合以及结果复现问题
Updated 8 months ago2
Access to checkpoints
Closed 8 months ago5
The checkpoint link in one drive cannot be opened
Closed 8 months ago1
Model zoo links expired
Closed 10 months ago2
Activitynet dataset
Closed a year ago2
About the dataloader.
Closed a year ago2
could you provide a demo code for test the video in the wild?
Updated a year ago
关于OSError: [Errno 5] Input/output error
Closed a year ago1
关于k400数据集
Closed a year ago2
Zero-shot Video Performance.
Closed a year ago2
Pre-trained models
Closed a year ago2
Data prep and training time
Closed a year ago2
Training and testing on single dGPU
Closed a year ago2